{"benchmark_id":"mmlu-stem","name":"MMLU-STEM","parent_benchmark":null,"categories":["math","physics","reasoning","chemistry"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"STEM-focused subset of the Massive Multitask Language Understanding benchmark, evaluating language models on science, technology, engineering, and mathematics topics including physics, chemistry, mathematics, and other technical subjects.","paper_link":"https://arxiv.org/abs/2009.03300","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.876901+00:00","updated_at":"2026-07-05T18:27:54.940660+00:00","statistics":{"total_models":2,"average_score":0.7865,"min_score":0.764,"max_score":0.809,"score_stddev":0.03181980515339475,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.809,"normalized_score":0.809,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"MMLU-STEM benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":32500000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.764,"normalized_score":0.764,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"MMLU-STEM benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":14700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}